NCT04473326: REINFORCE

Reinforcement Learning in Diabetes Mellitus Trial

Completed NA Results posted Last updated 8 February 2023

What this trial tests

NA trial testing Reinforcement Learning in Diabetes Mellitus, Type 2 in 60 participants. Completed in 28 January 2022.

Timeline

4 February 2021

Primary endpoint
4 January 2022

28 January 2022

Quick facts

Lead sponsor	Brigham and Women's Hospital
Phase	NA
Status	Completed
Study type	INTERVENTIONAL
Allocation	randomized
Design	parallel
Masking	double
Primary purpose	health services research
Enrollment	60
Start date	4 February 2021
Primary completion	4 January 2022
Estimated completion	28 January 2022
Sites	1 location across United States

Drugs / interventions tested

• Reinforcement Learning

Conditions studied

• Diabetes Mellitus, Type 2 — all drugs for Diabetes Mellitus, Type 2 →
• Medication Adherence — all drugs for Medication Adherence →

Sponsor

Brigham and Women's Hospital

Who can join

Adults 18 to 84, any sex, with Diabetes Mellitus, Type 2 or Medication Adherence. Patients with the condition only — healthy volunteers not accepted.

Results — posted to ClinicalTrials.gov

Per-arm endpoint measurements with 95% confidence intervals where reported. Source: trial results section.

Medication Adherence Primary · 6 months

Medication adherence to type 2 diabetes oral medications (averaged) as measured by the number of dates and times of pillbottle openings in the electronic pill bottles

Group	Value	95% CI
Reinforcement Learning Intervention Arm	74	± 31
Control Arm	68	± 29

Glycemic Control Secondary · 6 months

Change in glycated hemoglobin A1c from baseline to end of the 6-month follow-up

Group	Value	95% CI
Reinforcement Learning Intervention Arm	-0.82	± 1.19
Control Arm	-1.20	± 2.28

Sponsor's own description

Reinforcement learning is an advanced analytic method that discovers each individual's pattern of responsiveness by observing their actions and then implements a personalized strategy to optimize individuals' behaviors using trial and error. The goal of this pilot study is to develop and test a novel reinforcement learning-enhanced text messaging program to support medication adherence in patients with type 2 diabetes. Type 2 diabetes is an optimal condition in which to test this program, as it is one of the most prevalent chronic conditions in the US adult population and requires most patients to be on daily or twice daily doses of medications. This pilot study will be a parallel randomized pragmatic trial comparing medication adherence and clinical outcomes for adults aged 18-84 with type 2 diabetes who are prescribed 1-3 daily oral medications for this disease. Participants will be randomized to one of two arms for the duration of the study period: (1) a reinforcement learning intervention arm with up to daily, tailored text messages based on time-varying treatment-response patterns; or (2) a control arm with up to daily, un-tailored text messages. Our outcomes of interest will be medication adherence, as measured by electronic pill bottles, and HbA1c levels.

Publications & conference data

2 peer-reviewed publications reference this trial (live from Europe PMC):

1. The impact of using reinforcement learning to personalize communication on medication adherence: findings from the REINFORCE trial.
   Lauffenburger JC, Yom-Tov E, Keller PA, McDonnell ME, et al · · 2024 · cited 11× · PMID 38374424 · DOI 10.1038/s41746-024-01028-5
2. REinforcement learning to improve non-adherence for diabetes treatments by Optimising Response and Customising Engagement (REINFORCE): study protocol of a pragmatic randomised trial.
   Lauffenburger JC, Yom-Tov E, Keller PA, McDonnell ME, et al · · 2021 · cited 11× · PMID 34862289 · DOI 10.1136/bmjopen-2021-052091